Older Versus Younger

Population Pyramid

Photo by Paolo Bendandi on Unsplash

Count your age by friends, not years. Count your life by smiles, not tears.
— John Lennon

Ingest

age, gender, year, and population

df <- read.csv('archetypes/older-versus-younger/IHME_GBD_2017_POP.csv', header = TRUE, stringsAsFactors = FALSE, encoding = "UTF-8")
df

Wrangle

filter, remove duplicates, and transpose values

age_levels <- c(
     "Under 5",
     "5 to 9",
     "10 to 14",
     "15 to 19",
     "20 to 24",
     "25 to 29",
     "30 to 34",
     "35 to 39",
     "40 to 44",
     "45 to 49",
     "50 to 54",
     "55 to 59",
     "60 to 64",
     "65 to 69",
     "70 to 74",
     "75 to 79",
     "80 to 84",
     "85 to 89",
     "90 to 94",
     "95 plus")


# Select and filter rows
# unique(df$age_group_name)
# unique(df$location_name)
df_wrangle  <- df[,c(2,4,6,7,11)]%>% 
   filter(str_detect(location_name, 'SDI'))%>%
   filter(sex_name!="Both")%>%
   filter(age_group_name %in% age_levels) %>% 
   filter(year_id == 2017)

# Remove duplicate records
df_wrangle <- unique(df_wrangle)

## barplots for male populations goes to the left (thus negative sign)
df_wrangle$val <- ifelse(df_wrangle$sex_name == "Male", -1 * df_wrangle$val, df_wrangle$val)
df_wrangle

Plot

with socio-demographic Index (SDI) definitions

The Socio-Demographic Index (SDI) is: “A summary measure that identifies where countries or other geographic areas sit on the spectrum of development. Expressed on a scale of 0 to 1, SDI is a composite average of the rankings of the incomes per capita, average educational attainment, and fertility rates of all areas in the GBD study.”

theme_opts <- theme(
    text = element_text(family = "inconsolata"), 
    plot.title = element_text(color = "black", size = 14, face = "bold"),
    plot.subtitle = element_text(color = "black", size = 12),
    plot.caption = element_text(color = "#555555", size = 10),
    axis.title.x = element_blank(),
    axis.title.y = element_blank(),
    axis.text = element_text(family = "inconsolata", size = 14),
    panel.border = element_blank(),
    panel.background = element_blank(),
    panel.grid.minor = element_blank(),
    panel.grid.major.x = element_blank(),
    legend.title = element_blank(),
    legend.text = element_text(color = "black", size = 11),
    legend.position='bottom'
)

series_palette <- c(
  "Low SDI" = "#E53935",
  "Low-middle SDI" = "#FB8C00",
  "Middle SDI" = "#90A4AE",
  "High-middle SDI" = "#B0BEC5",
  "High SDI" = "#CFD8DC"
)

gender_map <- data.frame(
    gender = c("Male", "Female"),
    x = c("95 plus", "95 plus"),
    y = c(-50000000, 50000000)
)

v1 <- ggplot() + 
  geom_step(data=subset(df_wrangle, sex_name == "Female"), aes(x = factor(age_group_name, levels = age_levels ), y = val, color = location_name, group = location_name), size = 2) +
  geom_step(data=subset(df_wrangle, sex_name == "Male"), aes(x = factor(age_group_name, levels = age_levels ), y = val, color = location_name, group = location_name), size = 2) +
  geom_text(data = gender_map, aes(x = x, y = y, label = gender), size = 6, color = "black", vjust = 0.0, nudge_x = 0.1, hjust = 0.5, family = "inconsolata") +
  scale_y_continuous(name="Population (millions)",breaks=c(-100000000,-50000000,0,50000000,100000000), labels = c("100m","50m","0","50m","100m")) +
  scale_color_manual(values = series_palette) +
  coord_flip() +
  theme_minimal() +
  theme_opts  

girafe(ggobj = v1, width_svg = 1280/72, height_svg = 1080/72,
       options = list(opts_sizing(rescale = FALSE, width = 1.0))
)

Plot

with center axis

age_df <- data.frame( age_level = age_levels )

v2 <- ggplot() + 
  geom_step(data=subset(df_wrangle, sex_name == "Female"), aes(x = factor(age_group_name, levels = age_levels ), y = val, color = location_name, group = location_name), size = 2) +
  geom_step(data=subset(df_wrangle, sex_name == "Male"), aes(x = factor(age_group_name, levels = age_levels ), y = val, color = location_name, group = location_name), size = 2) +
  geom_text(data = gender_map, aes(x = x, y = y, label = gender), size = 6, color = "black", vjust = 0.0, nudge_x = 0.1, hjust = 0.5, family = "inconsolata") +
  geom_label(data = age_df, aes(x = age_level, y = 0, label = age_level), size = 4, color = "black", vjust = 0.5, hjust = 0.5, family = "inconsolata") +
  scale_y_continuous(name="Population(millions)",breaks=c(-100000000,-50000000,0,50000000,100000000), labels = c("100m","50m","0","50m","100m")) +
  scale_color_manual(values = series_palette) +
  coord_flip() +
  theme_minimal() +
  theme_opts +
  theme(
    axis.text.y = element_blank()
  )

girafe(ggobj = v2, width_svg = 1280/72, height_svg = 1080/72,
       options = list(opts_sizing(rescale = FALSE, width = 1.0))
)

References

The citations and data sources used for this case

Narrative sources: Global Burden of Disease Study 2017 (GBD 2017) Population Estimates 1950-2017, GO
Data sources: SDI, GO